|
Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Environmental Science / Faculty of Environmental Earth Science >
Peer-reviewed Journal Articles, etc >
Post-typhoon forest damage estimation using multiple vegetation indices and machine learning models
| Title: | Post-typhoon forest damage estimation using multiple vegetation indices and machine learning models |
| Authors: | Chen, Xinyu Browse this author | | Avtar, Ram Browse this author →KAKEN DB | | Umarhadi, Deha Agus Browse this author | | Louw, Albertus Stephanus Browse this author | | Shrivastava, Sourabh Browse this author | | Yunus, Ali P. Browse this author | | Khedher, Khaled Mohamed Browse this author | | Takemi, Tetsuya Browse this author →KAKEN DB | | Shibata, Hideaki Browse this author →KAKEN DB |
| Keywords: | Forest damage | | Remote sensing | | Vegetation indices | | Multispectral classification | | CLASlite |
| Issue Date: | Dec-2022 |
| Publisher: | Elsevier |
| Journal Title: | Weather and Climate Extremes |
| Volume: | 38 |
| Start Page: | 100494 |
| Publisher DOI: | 10.1016/j.wace.2022.100494 |
| Abstract: | The frequency and intensity of typhoons have increased due to climate change. These climate change-induced disasters have caused widespread damage to forests. Evaluation of the effects of typhoons on forest ecosys-tems is often complex and challenging, mainly because of their sporadic nature. In this paper, we compared existing forest damage estimation techniques with the goal of identifying their respective advantages and suit-able use cases. We considered Hokkaido in northern Japan as a case study, where three typhoons successively struck in 2016 and led to forest destruction. Forest damage was estimated from Landsat 8 imagery by three approaches, namely using vegetation damage indices (DVDI, DNDVI and & UDelta;EVI), using supervised classification with Random Forest (RF) and Support Vector Machines (SVM) and finally by using the commercial CLASlite software with built-in methods to detect forest disturbance. Machine learning classifiers obtained the highest damage assessment accuracy, but intensive computation and complex processing steps were required. The RF and SVM classifiers gave the highest accuracies when using Fractional Cover as a predictor variable (Overall Accuracy = 80.36% in both cases, and ROC AUC values of 0.89 and 0.88, respectively.) Among the vegetation damage indices, DNDVI produced the highest accuracy (AUC = 0.85, OA = 77.68%).The most damaged areas were on the windward slopes, where forest patches were exposed to the brunt of the typhoon winds. Forest damage also peaked at the highest elevations in the study area, possibly representing exposed hilltops. Methods and findings presented in this study can help stakeholders to implement more effective forest damage monitoring after typhoons and other extreme weather events in the future. |
| Type: | article |
| URI: | http://hdl.handle.net/2115/87094 |
| Appears in Collections: | 環境科学院・地球環境科学研究院 (Graduate School of Environmental Science / Faculty of Environmental Earth Science) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
|
